NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY7RGX8XSS181463WE53VTM
Run Details
Model:
Grok 4
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
32.1s
Cost:
$0.014159
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
67.75%
Matches word count
(details)
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 20 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
The misty streets of Eldridge concealed dark secrets as Detective Harlan arrived at the grand yet foreboding Blackwell mansion under moonlight. He stepped out of his weathered sedan, gravel crunching beneath his boots, while distant thunder rumbled ominously in the night sky. Pushing open the creaking front door, he entered a dimly lit foyer adorned with antique portraits staring down accusingly at him. A faint metallic scent hung in the air, mingling with the musty odor of old books and forgotten memories from years past. Upstairs, a scream had echoed earlier, drawing him here, but now silence enveloped the house like a suffocating shroud of mystery. Harlan climbed the spiral staircase cautiously, his hand gripping the revolver tightly, heart pounding with each deliberate step he took. At the top, he found the study door ajar, revealing a chaotic scene of overturned furniture and scattered papers everywhere. In the center lay the body of millionaire Elias Blackwell, blood pooling around his head from a brutal, fatal wound. No weapon was visible nearby, and the window stood open, curtains billowing as if someone had just fled into the night. Harlan knelt to examine the corpse, noting the absence of struggle marks, suggesting the killer was known to the victim somehow.
created_at
"2026-02-20T19:17:24.531Z"
2/20/2026, 7:17:24 PM
model
"x-ai/grok-4-07-09"
4/7/2009, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
23734
moderation_latency
(null)
generation_time
32061
tokens_prompt
46
tokens_completion
338
native_tokens_prompt
719
native_tokens_completion
902
native_tokens_completion_images
0
native_tokens_reasoning
651
native_tokens_cached
679
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
usage
0.01415925
router
(null)
provider_responses
0
endpoint_id
"d40bef9d-6936-4c57-9749-bf7399de4a77"
id
"fe325a4f-ace1-e092-4b64-d2508d0d0a59"
is_byok
false
latency
184
model_permaslug
"x-ai/grok-4-07-09"
4/7/2009, 12:00:00 AM
provider_name
"xAI"
status
200
api_type
"completions"
id
"gen-1771615044-2c7XzJD3eflFBuk5iGlp"
upstream_id
"fe325a4f-ace1-e092-4b64-d2508d0d0a59"
total_cost
0.01415925
cache_discount
0.00152775
upstream_inference_cost
0
provider_name
"xAI"
Evaluation details
Result
Evaluator
Details
Meta Data
67.75%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
21
1
21
2
21
3
22
4
21
5
20
6
20
7
20
8
21
9
21